© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104802
    Prev
    Next
    INDEX
    Explanations

    quality of performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -2.33
    ൎ
    -2.19
    ကိုးကား
    -2.19
    後記
    -2.05
    辗
    -1.97
    \
    -1.94
     zusätz
    -1.93
    自分は
    -1.91
    aphne
    -1.91
     condenado
    -1.89
    POSITIVE LOGITS
    s
    2.34
    as
    2.30
     However
    2.22
    ortic
    1.91
     JUNIOR
    1.77
     of
    1.74
    袮
    1.73
     VETER
    1.70
     Vuelta
    1.67
     BIRTHDAY
    1.66
    Activations Density 0.004%

    No Known Activations